Machine Learning: A Study of STEM Undergraduates

Additional Funding Sources

The funding for this project was supported or partially supported by Idaho State University Office of the Provost Undergraduate Research funds, and by the Idaho State University Career Path Internship Program.

Presentation Date

7-2019

Abstract

When STEM field related college professors and philanthropists are looking for candidates for scholarships, many are trying to determine the best return for the money they are donating. As such, retention in the field is a large component of many expectations for students who receive scholarships. Through the use of a Logistics Regression model and a Random Forrest statistical model, the aim of this study is to identify key factors as to why a student would switch from a STEM major to something non-STEM. From there, we would like to create and verify the accuracy of a model which predicts whether a student will graduate with a STEM or non-STEM based major.

Comments

T41

This document is currently not available here.

Share

COinS
 

Machine Learning: A Study of STEM Undergraduates

When STEM field related college professors and philanthropists are looking for candidates for scholarships, many are trying to determine the best return for the money they are donating. As such, retention in the field is a large component of many expectations for students who receive scholarships. Through the use of a Logistics Regression model and a Random Forrest statistical model, the aim of this study is to identify key factors as to why a student would switch from a STEM major to something non-STEM. From there, we would like to create and verify the accuracy of a model which predicts whether a student will graduate with a STEM or non-STEM based major.